Engineering and Technology
| Open Access | Cognitive Firewalls: Mitigating LLM-Powered Social Engineering Through Personality-Aware Behavioral Analytics and Automated Response Systemscc
Kenjiro S. Watanabe , Independent Researcher, LLM Threat Mitigation & Adaptive Behavioral Modelling, Tokyo, JapanAbstract
Background: The rapid advancement of Large Language Models (LLMs) has fundamentally altered the cybersecurity landscape, shifting the paradigm from technical exploitation to cognitive manipulation. Malicious actors now leverage generative AI to automate high-precision social engineering attacks, utilizing Open Source Intelligence (OSINT) to craft hyper-personalized spear-phishing campaigns at scale. Methods: This study analyzes the intersection of personality psychology—specifically the Big Five personality traits—and generative AI capabilities. We examine the theoretical framework of LLM-powered attacks, where attackers predict victim personality traits from digital footprints to tailor psychological triggers. We further evaluate the efficacy of counter-measures rooted in User Behavior Analytics (UBA) and AI-driven instantaneous response systems. Results: Analysis suggests that traditional signature-based detection systems are insufficient against LLM-generated content which lacks typical phishing indicators. However, defense mechanisms that integrate personality-aware baselines and behavioral anomaly detection demonstrate a higher potential for identifying synthetic social engineering attempts. Conclusion: We propose a "Cognitive Firewall" framework that combines psychological resilience training with automated, AI-driven behavioral monitoring. As LLMs lower the barrier for sophisticated attacks, defensive strategies must evolve to protect the human layer through proactive, context-aware algorithmic intervention.
Keywords
Large Language Models, Social Engineering, User Behavior Analytics, Big Five Personality Traits
References
Rajgopal, P. R. . (2025). AI Threat Countermeasures: Defending Against LLM-Powered Social Engineering. International Journal of IoT, 5(02), 23-43. https://doi.org/10.55640/ijiot-05-02-03
Liu, X., Zhang, X., & Wang, C. (2020). "DDoS Attacks on E-Commerce Systems: Vulnerabilities and Solutions." Journal of Cybersecurity, 8(2), 109-119.
Luo, X., Brody, R., Seazzu, A., & Burd, S. (2018). User behavior analytics: Applications and challenges in cybersecurity. Computers & Security, 74, 93-111.
Matthias, G., Gadepalli, N., & Jain, A. (2021). "AI for Instantaneous Response to Cybersecurity Incidents." Journal of Cybersecurity and Privacy, 5(2), 101-115.
McCray, K. L. (2023). Vulnerabilities and Threats in Mobile Banking that Financial Institutions Must Understand to Reduce Mobile Banking Fraud (Doctoral dissertation, Marymount University).
Sen, R., Heim, G., & Zhu, Q. (2022). Artificial intelligence and machine learning in cybersecurity: Applications, challenges, and opportunities for mis academics. Communications of the Association for Information Systems, 51(1), 28.
Sengupta, S., Kambhampati, S., & Chaudhuri, B. (2020). "Cyberattack Mitigation with AI-Based Response Automation." Journal of Network and Computer Applications, 164, 102706.
An, G., Levitan, S. I., Hirschberg, J., & Levitan, R. (2018). Deep personality recognition for deception detection. In INTERSPEECH, pp. 421–425.
Anawar, S., Kunasegaran, D. L., Mas’ud, M. Z., Zakaria,
N. A., et al. (2019). Analysis of phishing susceptibility in a workplace: a big-five personality perspectives. J Eng Sci Technol, 14(5), 2865–2882.
Asfour, M., & Murillo, J. C. (2023). Harnessing large language models to simulate realistic human responses to social engineering attacks: A case study. International Journal of Cybersecurity Intelligence & Cybercrime, 6(2), 21–49.
Evangelista, J.R.G., Sassi, R.J., Romero, M., Napolitano, D. (2021). Systematic literature review to investigate the application of open source intelligence (osint) with artificial intelligence. Journal of Applied Security Research 16(3), 345–369.
Azucar, D., Marengo, D., & Settanni, M. (2018). Predicting the big 5 personality traits from digital footprints on social media: A meta-analysis. Personality and Individual Differences, 124, 150–159.
Cialdini, R.B. (1995). Principles and techniques of social influence. Advanced Social Psychology, 256, 281.
Danner, D., Rammstedt, B., Bluemke, M., Lechner, C., Berres, S., Knopf, T., Soto, C., & John, O.P. (2016). Die deutsche version des big five inventory 2 (bfi-2). Zusammenstellung sozialwissenschaftlicher Items und Skalen (ZIS).
Deshpande, A., Murahari, V., Rajpurohit, T., Kalyan, A., & Narasimhan, K. (2023). Toxicity in chatgpt: Analyzing persona-assigned language models. arXiv preprint arXiv:2304.05335.
Download and View Statistics
Copyright License
Copyright (c) 2025 Kenjiro S. Watanabe
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain the copyright of their manuscripts, and all Open Access articles are disseminated under the terms of the Creative Commons Attribution License 4.0 (CC-BY), which licenses unrestricted use, distribution, and reproduction in any medium, provided that the original work is appropriately cited. The use of general descriptive names, trade names, trademarks, and so forth in this publication, even if not specifically identified, does not imply that these names are not protected by the relevant laws and regulations.